ch12 - Chapter 12 Instrumental Variables Regression...

Info iconThis preview shows pages 1–5. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Chapter 12 Instrumental Variables Regression Instrumental Variables Regression Recall the least square assumption #1: The error term u i has conditional mean zero given X i : E ( u i j X i ) = 0. When the regressor X is correlated with the error term, the assumption is violated. I If corr ( X i , u i ) 6 = 0, E ( u i j X i ) must be nonzero. Instrumental variables (IV) regression solves this problem. The IV Model and Assumptions Consider the population regression model Y i = + 1 X i + u i , i = 1, ..., n , If u i and X i are correlated, the OLS estimator is inconsistent. IV estimation uses an additional instrumental variable (or simply instrument) Z to isolate the part of X that is uncorrelated with u i . The IV Model and Assumptions Endogeneity and exogeneity: I Endogenous variables : Variables correlated with the error term I Exogenous variables : Variables uncorrelated with the error term A valid instrumental variable must satisfy two conditions: 1. Instrument relevance : corr ( Z i , X i ) 6 = 0....
View Full Document

Page1 / 11

ch12 - Chapter 12 Instrumental Variables Regression...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online